Subject: Q Science (General)
Year: 2018
Type: Article
Type: NonPeerReviewed
Title: Kernel smoothing method for hazard rate estimation: an application to Albanian firm survival
Author: Basha, Lule
Author: Muça, Markela
Abstract: The nonparametric approach to estimate hazard rates for lifetime data is flexible, model-free and data-driven. No shape assumption is imposed other than that the hazard function is a smooth function. Such an approach typically involves smoothing of an initial hazard estimate, with arbitrary choice of smoother. In this paper we demonstrate how we can obtain hazard estimators, by smoothing the increments of the Nelson-Aalen estimator for the cumulative hazard function, using kernel-type nonparametric method. This paper analyses the duration of the life for new entrant Albanian firms. We estimate firms’ hazards of failure and density function using some kernel estimators, based on a sample retrieved from the database of National Business Center. This sample contains 1000 firms, which were newly-established over the period January 2000 – December 2017. In this study censored data refers to those firms which were still alive at the time when the data was last updated. We also make a comparison between two classes of firms: Class I firms, Natural Person (PP), constituting 42.9% of the firms and Class II firms, Limited Liability Corporation (LLC), constituting 57.1% of the firms. All analysis were performed using R
Publisher: Faculty of Natural Sciences and Mathematics
Relation: https://eprints.unite.edu.mk/165/
Identifier: oai:eprints.unite.edu.mk:165
Identifier: https://eprints.unite.edu.mk/165/1/32.pdfIdentifier: Basha, Lule and Muça, Markela (2018) Kernel smoothing method for hazard rate estimation: an application to Albanian firm survival. Journal of Natural Sciences and Mathematics of UT, 3 (5-6). pp. 217-221. ISSN 2671-3039
